Search results

The paper aims to solve the problem of personnel intrusion identification within the limits of high-speed railways. It adopts the fusion method of millimeter wave radar and camera to improve the accuracy of object recognition in dark and harsh weather conditions.

This paper adopts the fusion strategy of radar and camera linkage to achieve focus amplification of long-distance targets and solves the problem of low illumination by laser light filling of the focus point. In order to improve the recognition effect, this paper adopts the YOLOv8 algorithm for multi-scale target recognition. In addition, for the image distortion caused by bad weather, this paper proposes a linkage and tracking fusion strategy to output the correct alarm results.

Simulated intrusion tests show that the proposed method can effectively detect human intrusion within 0–200 m during the day and night in sunny weather and can achieve more than 80% recognition accuracy for extreme severe weather conditions.

(1) The authors propose a personnel intrusion monitoring scheme based on the fusion of millimeter wave radar and camera, achieving all-weather intrusion monitoring; (2) The authors propose a new multi-level fusion algorithm based on linkage and tracking to achieve intrusion target monitoring under adverse weather conditions; (3) The authors have conducted a large number of innovative simulation experiments to verify the effectiveness of the method proposed in this article.

Effective rail surface defects detection method is the basic guarantee to manufacture high-quality rail. However, the existed visual inspection methods have disadvantages such as poor ability to locate the rail surface region and high sensitivity to uneven reflection. This study aims to propose a bionic rail surface defect detection method to obtain the high detection accuracy of rail surface defects under uneven reflection environments.

Through this bionic rail surface defect detection algorithm, the positioning and correction of the rail surface region can be computed from maximum run-length smearing (MRLS) and background difference. A saliency image can be generated to simulate the human visual system through some features including local grayscale, local contrast and edge corner effect. Finally, the meanshift algorithm and adaptive threshold are developed to cluster and segment the saliency image.

On the constructed rail defect data set, the bionic rail surface defect detection algorithm shows good recognition ability on the surface defects of the rail. Pixel- and defect-level index in the experimental results demonstrate that the detection algorithm is better than three advanced rail defect detection algorithms and five saliency models.

The bionic rail surface defect detection algorithm in the production process is proposed. Particularly, a method based on MRLS is introduced to extract the rail surface region and a multifeature saliency fusion model is presented to identify rail surface defects.

Perception has been identified as the main cause underlying most autonomous vehicle related accidents. As the key technology in perception, deep learning (DL) based computer vision models are generally considered to be black boxes due to poor interpretability. These have exacerbated user distrust and further forestalled their widespread deployment in practical usage. This paper aims to develop explainable DL models for autonomous driving by jointly predicting potential driving actions with corresponding explanations. The explainable DL models can not only boost user trust in autonomy but also serve as a diagnostic approach to identify any model deficiencies or limitations during the system development phase.

This paper proposes an explainable end-to-end autonomous driving system based on “Transformer,” a state-of-the-art self-attention (SA) based model. The model maps visual features from images collected by onboard cameras to guide potential driving actions with corresponding explanations, and aims to achieve soft attention over the image’s global features.

The results demonstrate the efficacy of the proposed model as it exhibits superior performance (in terms of correct prediction of actions and explanations) compared to the benchmark model by a significant margin with much lower computational cost on a public data set (BDD-OIA). From the ablation studies, the proposed SA module also outperforms other attention mechanisms in feature fusion and can generate meaningful representations for downstream prediction.

In the contexts of situational awareness and driver assistance, the proposed model can perform as a driving alarm system for both human-driven vehicles and autonomous vehicles because it is capable of quickly understanding/characterizing the environment and identifying any infeasible driving actions. In addition, the extra explanation head of the proposed model provides an extra channel for sanity checks to guarantee that the model learns the ideal causal relationships. This provision is critical in the development of autonomous systems.

Digital twin (DT) is an emerging technology that enables sophisticated interaction between physical objects and their virtual replicas. Although DT has recently gained significant attraction in both industry and academia, there is no systematic understanding of DT from its development history to its different concepts and applications in disparate disciplines. The majority of DT literature focuses on the conceptual development of DT frameworks for a specific implementation area. Hence, this paper provides a state-of-the-art review of DT history, different definitions and models, and six types of key enabling technologies. The review also provides a comprehensive survey of DT applications from two perspectives: (1) applications in four product-lifecycle phases, i.e. product design, manufacturing, operation and maintenance, and recycling and (2) applications in four categorized engineering fields, including aerospace engineering, tunneling and underground engineering, wind engineering and Internet of things (IoT) applications. DT frameworks, characteristic components, key technologies and specific applications are extracted for each DT category in this paper. A comprehensive survey of the DT references reveals the following findings: (1) The majority of existing DT models only involve one-way data transfer from physical entities to virtual models and (2) There is a lack of consideration of the environmental coupling, which results in the inaccurate representation of the virtual components in existing DT models. Thus, this paper highlights the role of environmental factor in DT enabling technologies and in categorized engineering applications. In addition, the review discusses the key challenges and provides future work for constructing DTs of complex engineering systems.

An accurate detection of overhead ground wire under open surroundings with varying illumination is the premise of reliable line grasping with the off-line arm when the inspection robot cross obstacle automatically. This paper aims to propose an improved approach which is called adaptive homomorphic filter and supervised learning (AHSL) for overhead ground wire detection.

First, to decrease the influence of the varying illumination caused by the open work environment of the inspection robot, the adaptive homomorphic filter is introduced to compensation the changing illumination. Second, to represent ground wire more effectively and to extract more powerful and discriminative information for building a binary classifier, the global and local features fusion method followed by supervised learning method support vector machine is proposed.

Experiment results on two self-built testing data sets A and B which contain relative older ground wires and relative newer ground wire and on the field ground wires show that the use of the adaptive homomorphic filter and global and local feature fusion method can improve the detection accuracy of the ground wire effectively. The result of the proposed method lays a solid foundation for inspection robot grasping the ground wire by visual servo.

This method AHSL has achieved 80.8 per cent detection accuracy on data set A which contains relative older ground wires and 85.3 per cent detection accuracy on data set B which contains relative newer ground wires, and the field experiment shows that the robot can detect the ground wire accurately. The performance achieved by proposed method is the state of the art under open environment with varying illumination.

At airport security checkpoints, baggage screening is aimed to prevent transportation of prohibited and potentially dangerous items. Observing the projection images generated by X-rays scanner is a critical method. However, when multiple objects are stacked on top of each other, distinguishing objects only by a two-dimensional picture is difficult, which prompts the demand for more precise imaging technology to be investigated for use. Reconstructing from 2D X-ray images to 3D-computed tomography (CT) volumes is a reliable solution.

To more accurately distinguish the specific contour shape of items when stacked, multi-information fusion network (MFCT-GAN) based on generative adversarial network (GAN) and U-like network (U-NET) is proposed to reconstruct from two biplanar orthogonal X-ray projections into 3D CT volumes. The authors use three modules to enhance the reconstruction qualitative and quantitative effects, compared with the original network. The skip connection modification (SCM) and multi-channels residual dense block (MRDB) enable the network to extract more feature information and learn deeper with high efficiency; the introduction of subjective loss enables the network to focus on the structural similarity (SSIM) of images during training.

On account of the fusion of multiple information, MFCT-GAN can significantly improve the value of quantitative indexes and distinguish contour explicitly between different targets. In particular, SCM enables features more reasonable and accurate when expanded into three dimensions. The appliance of MRDB can alleviate problem of slow optimization during the late training period, as well as reduce the computational cost. The introduction of subjective loss guides network to retain more high-frequency information, which makes the rendered CT volumes clearer in details.

The authors' proposed MFCT-GAN is able to restore the 3D shapes of different objects greatly based on biplanar projections. This is helpful in security check places, where X-ray images of stacked objects need to be distinguished from the presence of prohibited objects. The authors adopt three new modules, SCM, MRDB and subjective loss, as well as analyze the role the modules play in 3D reconstruction. Results show a significant improvement on the reconstruction both in objective and subjective effects.

The behavioral decision-making of digital-self is one of the important research contents of the network of crowd intelligence. The factors and mechanisms that affect decision-making have attracted the attention of many researchers. Among the factors that influence decision-making, the mind of digital-self plays an important role. Exploring the influence mechanism of digital-selfs’ mind on decision-making is helpful to understand the behaviors of the crowd intelligence network and improve the transaction efficiency in the network of CrowdIntell.

In this paper, the authors use behavioral pattern perception layer, multi-aspect perception layer and memory network enhancement layer to adaptively explore the mind of a digital-self and generate the mental representation of a digital-self from three aspects including external behavior, multi-aspect factors of the mind and memory units. The authors use the mental representations to assist behavioral decision-making.

The evaluation in real-world open data sets shows that the proposed method can model the mind and verify the influence of the mind on the behavioral decisions, and its performance is better than the universal baseline methods for modeling user interest.

In general, the authors use the behaviors of the digital-self to mine and explore its mind, which is used to assist the digital-self to make decisions and promote the transaction in the network of CrowdIntell. This work is one of the early attempts, which uses neural networks to model the mental representation of digital-self.

The purpose of this paper aims to model interaction relationship of traffic agents for motion prediction, which is critical for autonomous driving. It is obvious that traffic agents’ trajectories are influenced by physical lane rules and agents’ social interactions.

In this paper, the authors propose the social relation and physical lane aggregator for multimodal motion prediction, where the social relations of agents are mainly captured with graph convolutional networks and self-attention mechanism and then fused with the physical lane via the self-attention mechanism.

The proposed methods are evaluated on the Waymo Open Motion Dataset, and the results show the effectiveness of the proposed two feature aggregation modules for trajectory prediction.

This paper proposes a new design method to extract traffic interactions, and the attention mechanism is used in each part of the model to extract and fuse different relational features, which is different from other methods and improves the accuracy of the LSTM-based trajectory prediction method.

This study aims to summarize the critical issues in medical federated learning and applicable solutions. Also, detailed explanations of how federated learning techniques can be applied to the medical field are presented. About 80 reference studies described in the field were reviewed, and the federated learning framework currently being developed by the research team is provided. This paper will help researchers to build an actual medical federated learning environment.

Since machine learning techniques emerged, more efficient analysis was possible with a large amount of data. However, data regulations have been tightened worldwide, and the usage of centralized machine learning methods has become almost infeasible. Federated learning techniques have been introduced as a solution. Even with its powerful structural advantages, there still exist unsolved challenges in federated learning in a real medical data environment. This paper aims to summarize those by category and presents possible solutions.

This paper provides four critical categorized issues to be aware of when applying the federated learning technique to the actual medical data environment, then provides general guidelines for building a federated learning environment as a solution.

Existing studies have dealt with issues such as heterogeneity problems in the federated learning environment itself, but those were lacking on how these issues incur problems in actual working tasks. Therefore, this paper helps researchers understand the federated learning issues through examples of actual medical machine learning environments.